In John Gruber’s article about Apple Intelligence, he writes about the server impact:

As things stand, with only devices using M-series chips or the A17 or later eligible, Apple is going to be on the hook for an enormous amount of server-side computation with Private Cloud Compute. They’d be on the hook for multiples of that scale if they enabled Apple Intelligence for older iPhones, with those older iPhones doing none of the processing on-device.

Also, people are going to use this more than today’s Siri. How often will it need to go to the cloud? Seems very difficult to predict the scale.